Soft-Bubble grippers for robust and perceptive manipulation

Abstract

Manipulation in cluttered environments like homes requires stable grasps, precise placement and robustness against external contact. We present the Soft-bubble gripper system with a highly compliant gripping surface and dense-geometry visuotactile sensing, capable of multiple kinds of tactile perception. We first present various mechanical design advances and a fabrication technique to deposit custom patterns to the internal surface of the sensor that enable tracking of shearinduced displacement of the manipuland. The depth maps output by the internal imaging sensor are used in an in-hand proximity pose estimation framework -the method better captures distances to corners or edges on the manipuland geometry. We also extend our previous work on tactile classification and integrate the system within a robust manipulation pipeline for cluttered home environments. The capabilities of the proposed system are demonstrated through robust execution multiple real-world manipulation tasks. A video of the system in action can be found here.

Punyo-1: Soft tactile-sensing upper-body robot for large object manipulation and physical human interaction

“…Effectively using compliant contacts all over the body was demonstrated by Alspach et al [15], in which pressure-based feedback informed grasping of unmodeled objects. Inspired by these ideas, a gripper developed by Toyota Research Institute (TRI), known as the Soft-bubble (or Punyo) gripper [16], [17], incorporates highly compliant tactile sensing fingers [18] and not only maintains passively stable grasps but leverages multi-modal sensing to detect contact and manipuland state.…”

“…7: Soft-bubble "paw" module end effectors on our system. ules [16] and are able to sense internal pressure, dense contact geometry depth images, contact patches, and shear forces. The paws are used in both whole-body enveloping grasps like those shown in Fig.…”

Variable compliance and geometry regulation of Soft-Bubble grippers with active pressure control

“…In previously demonstrated results, dense optic flow techniques [19] have been successfully employed for tracking external shear and slip in inflated camera-based tactile sensors [20] through the tracking of internal surface visual markers from within the sensor itself [6].…”

“…One possibility towards achieving these goals is to leverage air-filled robotic structures. In this context, Soft-bubble grippers are a recently demonstrated compliant gripper [6] whose fingers include a depth camera-based tactile sensor ensconced in an extremely soft air-filled membrane structure [7]. The mechanism of the Soft-bubble finger itself consists of no moving parts and the mechanical separation of the imaging sensor and the inflated structure enables seamless decoupling of the compliance from the tactile sensing.…”

“…Previously, the tracking of shear forces was enabled by tracking the motion of markers printed on the elastic surface. In this paper we present an extension of the algorithm in [6] that takes into account the geometry changes and stretching that can result from active pressure regulation and combine a so-called contact-patch estimator with the shear estimates.…”